Variance-Reduced Heterogeneous Federated Learning via Stratified Client Selection
This addresses communication bottlenecks in federated learning for distributed systems, though it appears incremental as it builds on existing client selection approaches.
The paper tackles the problem of high variance in client selection for communication-efficient federated learning under data heterogeneity, proposing a stratified client selection scheme that achieves better convergence and higher accuracy than state-of-the-art methods.
Client selection strategies are widely adopted to handle the communication-efficient problem in recent studies of Federated Learning (FL). However, due to the large variance of the selected subset's update, prior selection approaches with a limited sampling ratio cannot perform well on convergence and accuracy in heterogeneous FL. To address this problem, in this paper, we propose a novel stratified client selection scheme to reduce the variance for the pursuit of better convergence and higher accuracy. Specifically, to mitigate the impact of heterogeneity, we develop stratification based on clients' local data distribution to derive approximate homogeneous strata for better selection in each stratum. Concentrating on a limited sampling ratio scenario, we next present an optimized sample size allocation scheme by considering the diversity of stratum's variability, with the promise of further variance reduction. Theoretically, we elaborate the explicit relation among different selection schemes with regard to variance, under heterogeneous settings, we demonstrate the effectiveness of our selection scheme. Experimental results confirm that our approach not only allows for better performance relative to state-of-the-art methods but also is compatible with prevalent FL algorithms.